# Natural Language Inference on MNLI Syntactic Bias (in-distribution) Source: [Natural Language Inference on MNLI Syntactic Bias (in-distribution)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:04.978Z Evaluation of Natural Language Inference performance specifically on the in-distribution subset of the MNLI dataset designed to test syntactic bias. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Natural Language Inference | | Dataset (including any stated split) | MNLI Syntactic Bias (in-distribution) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LMinDirichlet | 84.3 | Not recorded | 68fa6b341e209131cea2cdc0 | | CE | 84.2 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoEDirichlet | 84.1 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMin | 84.1 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMinTemps | 84.1 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoETemps | 83.9 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvRDirichlet | 83.7 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFtDirichlet | 83.6 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvRTemps | 83.6 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFtTemps | 83 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoE | 82.8 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvR | 82.5 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFt | 81.8 | Not recorded | 68fa6b341e209131cea2cdc0 | ### LMinDirichlet Accuracy: 84.3. Result ID: 698e7112ffc3901de09d9eb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### CE Accuracy: 84.2. Result ID: 698e7112ffc3901de09d9ea8. [Reporting paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### PoEDirichlet Accuracy: 84.1. Result ID: 698e7112ffc3901de09d9eab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### LMin Accuracy: 84.1. Result ID: 698e7112ffc3901de09d9eb2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### LMinTemps Accuracy: 84.1. Result ID: 698e7112ffc3901de09d9eb3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### PoETemps Accuracy: 83.9. Result ID: 698e7112ffc3901de09d9eaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### InvRDirichlet Accuracy: 83.7. Result ID: 698e7112ffc3901de09d9eb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### DRiFtDirichlet Accuracy: 83.6. Result ID: 698e7112ffc3901de09d9eae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### InvRTemps Accuracy: 83.6. Result ID: 698e7112ffc3901de09d9eb0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### DRiFtTemps Accuracy: 83. Result ID: 698e7112ffc3901de09d9ead. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### PoE Accuracy: 82.8. Result ID: 698e7112ffc3901de09d9ea9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### InvR Accuracy: 82.5. Result ID: 698e7112ffc3901de09d9eaf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### DRiFt Accuracy: 81.8. Result ID: 698e7112ffc3901de09d9eac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.